# Is MNN-Pocket-0.3B SOTA?

Pending benchmarks. Announced Nov 4, 2026; no independent results yet.

As of Nov 22, 2026, MNN-Pocket-0.3B is pending benchmarks on isitsota: announced Nov 4, 2026, with no independent results on the boards we track yet.

The Alibaba Taobao MNN team's compact Chinese/English instruction-tuned text LLM, co-designed with its on-device MNN inference stack. Marketed as roughly 300M parameters (361.55M in HF safetensors metadata), with 32K deployed context and a lab-reported 173 MB INT4 W4A16 QAT MNN build. Apache-2.0 weights are public for local use; no public hosted API is confirmed.

Canonical: https://isitsota.com/m/mnn-pocket-0-3b
Last updated: 2026-11-08
Tracking since: 2026-11-08

## Announced facts

| Fact | Value |
| --- | --- |
| Lab | Alibaba Taobao MNN |
| Announced | Nov 4, 2026 |
| API | Not yet |
| Open weights | Published |
| Parameters | ~300M advertised; 361.55M total safetensors parameters |
| Team and lineage | MNN Team, Taobao and Tmall Group of Alibaba; instruction-tuned from taobao-mnn/MNN-Pocket-0.3B-Base. This is a separate MNN team release, not attributed to the Qwen lab merely because a qwen3 tag appears |
| Architecture | 28 layers, hidden size 896, GQA with 14 query / 2 KV heads, tied input/output embeddings, 65,536 vocabulary; BF16 native checkpoint |
| Context | 32K supported in deployment; configuration/card lists 40,960 positions, not a claim of 40K deployed support |
| License | Apache-2.0 verified in model card and LICENSE.txt |
| Formats | Public Transformers safetensors, GGUF and MNN formats. MNN INT4 W4A16 quantization-aware build is advertised at 173 MB; GGUF Q4_1 uses the QAT checkpoint |
| Limitations | Team does not recommend reasoning-heavy advanced mathematics or long-horizon code generation; latency/throughput depends on hardware, backend and context |
| Related | Separate from Base and intermediate SFT checkpoints, DFlash2 auxiliary variants, and the non-autoregressive Dec decision model. GGUF/MNN packaging variants stay on this instruction-model page |
| Date evidence | Official alibaba/MNN README release note dated Nov 4, corroborated by a public HF discussion that day. Sep 23 repo creation and Sep 26 release-labelled commit do not independently prove historical public access |

Tags marked unsure are not stated on the lab's own pages.

## What would let us call it

Verdicts use only independent boards we already track. Two consecutive snapshots are required before any crown.

- [x] Publicly announced with a source
- [x] Usable by the public (API or weights)
- [ ] Listed on an independent board we track
- [ ] Enough results for a rank in a category
- [ ] Holds across two snapshots (crowns only)

## What the lab claims

Self-reported. Shown for context; not used in any verdict.

- Lab claim: INT4 W4A16 QAT deployment footprint is 173 MB. At 512-token context, decode reaches 466 tokens/s on iPad Pro M5 Metal (231 on its CPU); these are team measurements, not independent results.
- Lab claim: average across the team's 11 Chinese/English benchmarks is 50.00 for native precision and 49.59 for INT4.

## Sources

- REPO: [MNN team model card and weights](https://huggingface.co/taobao-mnn/MNN-Pocket-0.3B)
- REPO: [Official MNN README Nov 4 release news](https://github.com/alibaba/MNN) (2026-11-04)
- REPO: [Public HF discussion corroborating Nov 4 access](https://huggingface.co/taobao-mnn/MNN-Pocket-0.3B/discussions/1) (2026-11-04)
- REPO: [MNN-Pocket Apache-2.0 license](https://huggingface.co/taobao-mnn/MNN-Pocket-0.3B/blob/main/LICENSE.txt)
- LAB: [MNN team technical report](https://huggingface.co/taobao-mnn/MNN-Pocket-0.3B/blob/main/MNN-Pocket-0.3B-Technical-Report.pdf)

Tracking continues until an independent board lists it.

## Related

- Lab: [Alibaba Taobao MNN](https://isitsota.com/labs/taobao-mnn.md)
- All pending releases: https://isitsota.com/releases.md
- JSON: https://api.isitsota.com/v1/models/mnn-pocket-0-3b
